piqa_step02500: by models

Home Paper Code


SE predicted by accuracy

The typical standard errors between pairs of models on this dataset as a function of the absolute accuracy.

SE vs accuracy difference

The standard error of each model pair against their observed accuracy difference. Pairs below a reference line differ by more than the corresponding number of standard errors, i.e. they are statistically distinguishable at that level.

CDF of question level accuracy

Results table by model

model pass1 pass@count win_rate count SE(A) SE_x(A) SE_pred(A)
seed17495 65 65 5.74 1 1.1 NaN NaN
seed6529 64.9 64.9 5.49 1 1.1 NaN NaN
seed24762 64.5 64.5 5.13 1 1.1 NaN NaN
seed16385 64.5 64.5 5.53 1 1.1 NaN NaN
seed30841 64.4 64.4 5.3 1 1.1 NaN NaN
seed24734 64.2 64.2 5.1 1 1.1 NaN NaN
seed27712 64 64 5.13 1 1.1 NaN NaN
seed149 64 64 5.27 1 1.1 NaN NaN
seed14309 63.7 63.7 4.93 1 1.1 NaN NaN
seed6115 63.7 63.7 5.15 1 1.1 NaN NaN